Staff Engineer - AI Platform

Staff Engineer - AI Platform Location: India Founded in 2014, Circles is a global technology company reimagining the telco industry with its innovative SaaS platform, empowering telco operators worldwide to effortlessly launch innovative digital brands or refresh existing ones, accelerating their transformation into techcos. Today, Circles partners with leading telco operators across multiple countries and continents, including KDDI Corporation, Etisalat Group (e&), AT&T, and Telkomsel, creating blueprints for future telco and digital experiences enjoyed by millions of consumers globally. Besides its SaaS business, Circles operates three other distinct businesses: Circles.Life: A wholly-owned digital lifestyle telco brand based in Singapore, Circles.Life is powered by Circles’ SaaS platform and pioneering go-to-market strategies. It is the digital market leader in Singapore and has won numerous awards for marketing, customer service, and innovative product offerings beyond connectivity. Circles Aspire: A global provider of Communications Platform-as-a-Service (CPaaS) solutions. Its cloud-based Experience Cloud platform enables enterprises, service providers and developers to deliver and scale mobile, messaging, IoT, and connectivity services worldwide. Jetpac: Specializing in travel tech solutions, Jetpac provides seamless eSIM roaming for over 200 destinations and innovative travel lifestyle products, redefining connectivity for digital travelers. Jetpac was awarded Travel eSIM of the Year. Circles is backed by renowned global investors, including Peak XV Partners (formerly Sequoia), Warburg Pincus, Founders Fund, and EDBI (the investment arm of the Singapore Economic Development Board), with a track record of backing industry challengers. Standardized Job Title: Staff Software Engineer Role: Staff Engineer — AI Platform Location: Bangalore Role Summary: Leads the design and implementation of AI & CXOS systems. Owns critical technical decisions within the AI & CXOS  platform, drives best practices, and provides hands-on technical leadership. Bridges the gap between architectural vision and implementation, ensuring AI & CXOS systems are production-ready and maintainable. Expected to learn and adapt quickly as AI tools and best practices evolve. Key Responsibilities Build new features, enhance existing ones, and support them in production, focusing on the AI platform. Build reusable libraries or technology platforms that address multiple use cases. Work closely with Engineers to develop the best technical design, strategy, and drive execution to build capabilities into the platform. Own service for assigned services, including functional availability, correctness, and security. Own the delivery of various timelines, ensuring that key milestones are met and deliveries are of the highest quality. Establish and encourage the adoption of software development best practices across the team and the organization. Collaborate with non-technical stakeholders such as Product Managers, Designers, and Marketing. Encourage and mentor talented engineers, working with them to remove any roadblocks. Deploy and maintain enterprise-class RESTful web services. Own the engineering excellence and operational readiness of the service, driving the SLO, SLI, and SLA of the relevant services. Take ownership to drive quality via integration and unit test coverage. Dive deep into each issue, own reactive fixes, and execute long-term fixes, assisting other Support Engineers on complex RCA issues. Provide technical mentoring and L3 engineering support to other engineers. Core AI & ML Skills AI System Design Design and implement AI workflows and agent architectures using frameworks like LangGraph. Build production-grade RAG systems with appropriate chunking, retrieval, and response generation. Design conversation management with context handling, session state, and error recovery. Architect customer-facing AI features with proper validation, fallbacks, and graceful degradation. Implement tool orchestration patterns for connecting LLMs to existing APIs and services. LLM Integration Production implementation of LLM APIs with retry logic, fallbacks, and rate limit handling. Practical prompt engineering: system prompts, few-shot learning, structured outputs (JSON mode). Implement evaluation approaches for AI output quality (automated checks, regression testing). Optimize token usage and manage API costs effectively. Awareness of prompt versioning and systematic iteration practices. Data Pipelines for AI Build data ingestion pipelines for AI systems (document processing, embedding generation). Implement vector storage and retrieval workflows for RAG and search use cases. Design feedback loops from production AI usage back to improvement cycles. Basic data quality practices for AI inputs (validation, cleaning, deduplication). AI Safety & Quality Implement input validation and output filtering for production AI systems. Build or integrate content safety layers (keyword filters, classifier-based detection). Design guardrails that balance safety with usability (avoiding over-blocking). Implement logging and auditing for AI interactions to support compliance and debugging. Core Backend & Platform Engineering Backend Engineering Strong proficiency in Go, Node.js, or Java microservices. Design and optimize high-throughput APIs for production workloads. Database experience: SQL (PostgreSQL), NoSQL (Redis, MongoDB), and familiarity with vector stores. Event-driven architecture: Kafka, message queues, or streaming patterns. Infrastructure & DevOps Container orchestration (Kubernetes), CI/CD pipelines, and infrastructure as code. Performance profiling and optimization for API-heavy workloads. Cloud services: AWS/GCP compute, storage, and relevant AI services. AI Concepts & Knowledge Must Know How LLMs generate responses: tokens, probabilities, context windows, and temperature. Embeddings: what they are, how to choose embedding models, and similarity search basics. RAG fundamentals: indexing strategies, retrieval methods, and when RAG is the right approach. Agent patterns: tool use, function calling, multi-step reasoning, and when to use agents vs. simple chains. Prompt engineering practices: chain-of-thought, few-shot, structured outputs, and systematic testing. AI safety basics: prompt injection, jailbreaking, and practical mitigation approaches. Awareness of fine-tuning concepts and when fine-tuning might be considered over prompt-based solutions. Tools & Platforms Required LangGraph / LangChain for agent and workflow building. Claude SDK / OpenAI SDK for API integration. At least one vector database in practice (pgvector, Pinecone, Weaviate, or similar). AI observability tools (LangSmith, LangFuse) for tracing and debugging. AI workflow platforms for rapid prototyping. Python for AI scripting and prototyping. MCP or equivalent tool integration patterns. Mindset & Soft Skills Required Strong problem-solving: breaks down ambiguous AI problems into concrete, implementable tasks. Independent researcher: reads documentation and experiments before escalating. Good debugging skills across LLM calls, embeddings, retrieval, and API integrations. Mentoring ability: can teach AI concepts and patterns to less experienced team members. Clear technical writing for design docs and runbooks. Comfortable with rapid iteration: AI solutions often require experimentation over upfront specification. Quick learner who actively keeps up with the evolving AI landscape. Experience and General Requirements Around 10+ years of experience in software development of which 2 years are lead experience. Strong design and architectural experience in building various highly-scalable and highly-available products. Strong understanding of the SDLC Activities which include Analysis, Design, Development, Testing, Deployment and Post-Production Support etc.. Deep Dive, problem-solving, RCA and systematic thinking to reach the cause of issues. Able to work independently and multi-task effectively. Program at a system level and able to manage service stability. Excellent experience maintaining scalable, extensible code. Methodical in maintaining up to date documentation. Metric-driven mindset and obsessive about ensuring clean coding practices. Circles is committed to a diverse and inclusive workplace. We are an equal opportunity employer and do not discriminate on the basis of race, national origin, gender, disability or age. Data Protection and Privacy Statement By submitting an application for this position, you, as the applicant, or your authorised representative(s), consent toCircles’ Candidate Data Protection and Privacy Policy.You also agree to the collection, use, and/or disclosure of your personal data by us solely for recruitment purposes as specified in the Policy. You acknowledge that you have read and understood the Policy, are aware of your rights regarding your personal data, and accept the terms relating to international data transfers, where applicable. You further understand that you may withdraw consent at any time, which may affect our ability to consider your application. In instances where your personal data or application is submitted by a third party, it is understood that such third party has been duly authorised by you to disclose the relevant personal data and provide consent on your behalf, and that you have been made aware of this Policy. To all recruitment agencies: Circles will only acknowledge resumes shared by recruitment agencies if selected in our preferred supplier partnership program. Please do not forward resumes to our jobs alias, Circles, employees or any other company location. Circles will not be held accountable for any fees related to unsolicited resumes not uploaded via our ATS.